% Key papers for Spatiotemporal CNNs for action recognition (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2018_a_12787,
  title = {{A Closer Look at Spatiotemporal Convolutions for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Tran_A_Closer_Look_CVPR_2018_paper.html},
}

@inproceedings{cvpr2016_convolutional_11452,
  title = {{Convolutional Two-Stream Network Fusion for Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_can_12893,
  title = {{Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Hara_Can_Spatiotemporal_3D_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_video_20176,
  title = {{Video Swin Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2016_generating_55752,
  title = {{Generating Videos with Scene Dynamics}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7257},
}

@inproceedings{cvpr2017_spatiotemporal_12655,
  title = {{Spatiotemporal Multiplier Networks for Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_deep_12148,
  title = {{Deep Feature Flow for Video Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2016_spatiotemporal_56002,
  title = {{Spatiotemporal Residual Networks for Video Action Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7276},
}

@inproceedings{cvpr2016_dynamic_11508,
  title = {{Dynamic Image Networks for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_actionvlad_12041,
  title = {{ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_tdn_17971,
  title = {{TDN: Temporal Difference Networks for Efficient Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_temporal_16329,
  title = {{Temporal Pyramid Network for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2016_real_11788,
  title = {{Real-Time Action Recognition With Enhanced Motion Vector CNNs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_appearance_12843,
  title = {{Appearance-and-Relation Networks for Video Classification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Appearance-and-Relation_Networks_for_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_compressed_12910,
  title = {{Compressed Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wu_Compressed_Video_Action_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_mars_14488,
  title = {{MARS: Motion-Augmented RGB Stream for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_multiview_19404,
  title = {{Multiview Transformers for Video Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2017_spatiotemporal_12656,
  title = {{Spatiotemporal Pyramid Network for Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2020_teinet_103729,
  title = {{TEINet: Towards an Efficient Architecture for Video Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6836},
}

@inproceedings{cvpr2018_mict_13369,
  title = {{MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_MiCT_Mixed_3D2D_CVPR_2018_paper.html},
}